Antonio Mastropaolo

82 papers A* 7A 10B 1C 1Journal 60Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
An Empirical Study on the Effects of System Prompts in Instruction-Tuned Models for Code Generation.
CoRR
Zaiyu Cheng, Antonio Mastropaolo
2026 J jnl
Datasets, bias, licenses, and terms of use: A large and longitudinal study on the documentation of hugging face machine learning models.
Empir. Softw. Eng.
Federica Pepe, Vittoria Nardone, Antonio Mastropaolo, Gerardo Canfora, Gabriele Bavota, Massimiliano Di Penta
2026 J jnl
Developers and Generative AI: A Study of Self-Admitted Usage in Open Source Projects.
CoRR
Rosalia Tufano, Federica Pepe, Fiorella Zampetti, Antonio Mastropaolo, Ozren Dabic, Massimiliano Di Penta, Gabriele Bavota
2026 J jnl
Developers and generative AI: A study of self-admitted usage in open source projects.
Empir. Softw. Eng.
Rosalia Tufano, Federica Pepe, Fiorella Zampetti, Antonio Mastropaolo, Ozren Dabic, Massimiliano Di Penta, Gabriele Bavota
2026 J jnl
Editorial of the special issue in the journal of systems and software on reliable and secure large language models for software engineering.
J. Syst. Softw.
Antonio Mastropaolo, Pietro Liguori, Gabriele Bavota
2026 J jnl
Human or Machine? Rebuilding Trust in the Age of AI-Based Text Generation.
Computer
Antonio Mastropaolo
2026 J jnl
LLM-Powered Security Test Generation: Oracles, Vulnerability Probes, and Adversarial Inputs.
Computer
Antonio Mastropaolo, Rick Kuhn, Jeffrey M. Voas
2026 J jnl
Mind the Overlap: Trustworthy Evaluation for Large Code Models.
Computer
Antonio Mastropaolo
2026 J jnl
Not All Tokens Matter: Data-Centric Optimization for Efficient Code Summarization.
CoRR
Saima Afrin, Zaiyu Cheng, Tushar Sharma, Alexander Serebrenik, Massimiliano Di Penta, Antonio Mastropaolo
2026 J jnl
Parameter-Efficient Multi-Task Fine-Tuning in Code-Related Tasks.
CoRR
Md Zahidul Haque, Saima Afrin, Antonio Mastropaolo
2026 J jnl
Secrets in the Synapses: When Steganography Meets Large Language Models.
Computer
Antonio Mastropaolo
2026 J jnl
The Virtue of Hallucination: When AI Mistakes Make Software Safer.
Computer
Antonio Mastropaolo
2026 J jnl
Toward Reliable Security Operations Center Testing With Foundation Models.
Computer
Sophia Shahnami, Antonio Mastropaolo, Jeffrey M. Voas
2026 J jnl
Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering.
CoRR
Daniel Rodríguez-Cárdenas, Xiaochang Li, Marcos Macedo, Antonio Mastropaolo, Dipin Khati, Yuan Tian, Huajie Shao, Denys Poshyvanyk
2025 — conf
A Path Less Traveled: Reimagining Software Engineering Automation via a Neurosymbolic Paradigm.
SIGSOFT FSE Companion
Antonio Mastropaolo, Denys Poshyvanyk
2025 J jnl
A Path Less Traveled: Reimagining Software Engineering Automation via a Neurosymbolic Paradigm.
CoRR
Antonio Mastropaolo, Denys Poshyvanyk
2025 J jnl
A Systematic Literature Review of Parameter-Efficient Fine-Tuning for Large Code Models.
CoRR
Md Zahidul Haque, Saima Afrin, Antonio Mastropaolo
2025 J jnl
Breaking Bottlenecks in Large Language Model Inference With Adaptive Cache Management.
Computer
Antonio Mastropaolo
2025 J jnl
Code, Chaos, and Clarity: Neurosymbolic Approaches to Trustworthy Software Automation.
Computer
Antonio Mastropaolo
2025 J jnl
From Heuristics to Intelligence: Large Language Model-Driven Test Case Generation.
Computer
Antonio Mastropaolo, Rick Kuhn, Jeffrey M. Voas
2025 J jnl
From Triumph to Uncertainty: The Journey of Software Engineering in the AI Era.
ACM Trans. Softw. Eng. Methodol.
Antonio Mastropaolo, Camilo Escobar-Velásquez, Mario Linares-Vásquez
2025 J jnl
How Artificial Intelligence Is Reshaping Our Lives: A Framework to Unravel Its Complexities.
Computer
Antonio Mastropaolo
2025 A conf
Is Quantization a Deal-Breaker? Empirical Insights From Large Code Models.
ICSME
Saima Afrin, Bowen Xu, Antonio Mastropaolo
2025 J jnl
Is Quantization a Deal-breaker? Empirical Insights from Large Code Models.
CoRR
Saima Afrin, Bowen Xu, Antonio Mastropaolo
2025 J jnl
On the Effectiveness of LLM-as-a-Judge for Code Generation and Summarization.
IEEE Trans. Software Eng.
Giuseppe Crupi, Rosalia Tufano, Alejandro Velasco, Antonio Mastropaolo, Denys Poshyvanyk, Gabriele Bavota
2025 J jnl
On the Effectiveness of LLM-as-a-judge for Code Generation and Summarization.
CoRR
Giuseppe Crupi, Rosalia Tufano, Alejandro Velasco, Antonio Mastropaolo, Denys Poshyvanyk, Gabriele Bavota
2025 A conf
Optimizing Datasets for Code Summarization: Is Code-Comment Coherence Enough?
ICPC
Antonio Vitale, Antonio Mastropaolo, Rocco Oliveto, Massimiliano Di Penta, Simone Scalabrino
2025 J jnl
Optimizing Datasets for Code Summarization: Is Code-Comment Coherence Enough?
CoRR
Antonio Vitale, Antonio Mastropaolo, Rocco Oliveto, Massimiliano Di Penta, Simone Scalabrino
2025 J jnl
Pixels of Deception: How Evolutionary Algorithms Break AI Reliability.
Computer
Antonio Mastropaolo
2025 J jnl
Prompt Alchemy: Engineering the Magic of Code.
Computer
Antonio Mastropaolo
2025 J jnl
Quantizing Large Language Models for Code Generation: A Differentiated Replication.
CoRR
Alessandro Giagnorio, Antonio Mastropaolo, Saima Afrin, Massimiliano Di Penta, Gabriele Bavota
2025 — conf
Resource-Efficient & Effective Code Summarization.
Forge@ICSE
Saima Afrin, Joseph Call, Khai-Nguyen Nguyen, Oscar Chaparro, Antonio Mastropaolo
2025 J jnl
Resource-Efficient & Effective Code Summarization.
CoRR
Saima Afrin, Joseph Call, Khai-Nguyen Nguyen, Oscar Chaparro, Antonio Mastropaolo
2025 J jnl
Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation.
CoRR
Sen Fang, Weiyuan Ding, Antonio Mastropaolo, Bowen Xu
2025 J jnl
Smart but Costly? Benchmarking LLMs on Functional Accuracy and Energy Efficiency.
CoRR
Mohammad Javad Mehditabar, Saurabhsingh Rajput, Antonio Mastropaolo, Tushar Sharma
2025 J jnl
Smarter, Not Harder: Efficient Artificial Intelligence Training With Selective Data.
Computer
Antonio Mastropaolo
2025 J jnl
Toward Explaining Large Language Models in Software Engineering Tasks.
CoRR
Antonio Vitale, Khai-Nguyen Nguyen, Denys Poshyvanyk, Rocco Oliveto, Simone Scalabrino, Antonio Mastropaolo
2025 A conf
Toward Neurosymbolic Program Comprehension.
ICPC
Alejandro Velasco, Aya Garryyeva, David N. Palacio, Antonio Mastropaolo, Denys Poshyvanyk
2025 J jnl
Toward Neurosymbolic Program Comprehension.
CoRR
Alejandro Velasco, Aya Garryyeva, David N. Palacio, Antonio Mastropaolo, Denys Poshyvanyk
2025 A conf
Towards Generating the Rationale for Code Changes.
ICPC
Francesco Casillo, Antonio Mastropaolo, Gabriele Bavota, Vincenzo Deufemia, Carmine Gravino
2025 J jnl
When Databases Age: How SQL Server and MySQL Handle the Test of Time.
Computer
Antonio Mastropaolo
2024 A conf
A Taxonomy of Self-Admitted Technical Debt in Deep Learning Systems.
ICSME
Federica Pepe, Fiorella Zampetti, Antonio Mastropaolo, Gabriele Bavota, Massimiliano Di Penta
2024 J jnl
A Taxonomy of Self-Admitted Technical Debt in Deep Learning Systems.
CoRR
Federica Pepe, Fiorella Zampetti, Antonio Mastropaolo, Gabriele Bavota, Massimiliano Di Penta
2024 J jnl
Code Review Automation: Strengths and Weaknesses of the State of the Art.
CoRR
Rosalia Tufano, Ozren Dabic, Antonio Mastropaolo, Matteo Ciniselli, Gabriele Bavota
2024 J jnl
Code Review Automation: Strengths and Weaknesses of the State of the Art.
IEEE Trans. Software Eng.
Rosalia Tufano, Ozren Dabic, Antonio Mastropaolo, Matteo Ciniselli, Gabriele Bavota
2024 A* conf
Evaluating Code Summarization Techniques: A New Metric and an Empirical Characterization.
ICSE
Antonio Mastropaolo, Matteo Ciniselli, Massimiliano Di Penta, Gabriele Bavota
2024 A conf
How do Hugging Face Models Document Datasets, Bias, and Licenses? An Empirical Study.
ICPC
Federica Pepe, Vittoria Nardone, Antonio Mastropaolo, Gabriele Bavota, Gerardo Canfora, Massimiliano Di Penta
2024 A conf
How the Training Procedure Impacts the Performance of Deep Learning-based Vulnerability Patching.
EASE
Antonio Mastropaolo, Vittoria Nardone, Gabriele Bavota, Massimiliano Di Penta
2024 J jnl
How the Training Procedure Impacts the Performance of Deep Learning-based Vulnerability Patching.
CoRR
Antonio Mastropaolo, Vittoria Nardone, Gabriele Bavota, Massimiliano Di Penta
2024 J jnl
Log statements generation via deep learning: Widening the support provided to developers.
J. Syst. Softw.
Antonio Mastropaolo, Valentina Ferrari, Luca Pascarella, Gabriele Bavota
2024 — conf
On the Reform of the Italian Constitution: an Interdisciplinary Text Readability Analysis.
NL4AI@AI*IA
Calogero Jerik Scozzaro, Matteo Delsanto, Antonio Mastropaolo, Enrico Mensa, Luisa Revelli, Daniele Paolo Radicioni
2024 J jnl
The Rise and Fall(?) of Software Engineering.
CoRR
Antonio Mastropaolo, Camilo Escobar-Velásquez, Mario Linares-Vásquez
2024 A* conf
Toward Automatically Completing GitHub Workflows.
ICSE
Antonio Mastropaolo, Fiorella Zampetti, Gabriele Bavota, Massimiliano Di Penta
2024 A conf
Towards Summarizing Code Snippets Using Pre-Trained Transformers.
ICPC
Antonio Mastropaolo, Matteo Ciniselli, Luca Pascarella, Rosalia Tufano, Emad Aghajani, Gabriele Bavota
2024 J jnl
Towards Summarizing Code Snippets Using Pre-Trained Transformers.
CoRR
Antonio Mastropaolo, Matteo Ciniselli, Luca Pascarella, Rosalia Tufano, Emad Aghajani, Gabriele Bavota
2024 A conf
Unveiling ChatGPT's Usage in Open Source Projects: A Mining-based Study.
MSR
Rosalia Tufano, Antonio Mastropaolo, Federica Pepe, Ozren Dabic, Massimiliano Di Penta, Gabriele Bavota
2024 J jnl
Unveiling ChatGPT's Usage in Open Source Projects: A Mining-based Study.
CoRR
Rosalia Tufano, Antonio Mastropaolo, Federica Pepe, Ozren Dabic, Massimiliano Di Penta, Gabriele Bavota
2023 J jnl
Automated variable renaming: are we there yet?
Empir. Softw. Eng.
Antonio Mastropaolo, Emad Aghajani, Luca Pascarella, Gabriele Bavota
2023 B conf
Automatically Generating Dockerfiles via Deep Learning: Challenges and Promises.
ICSSP
Giovanni Rosa, Antonio Mastropaolo, Simone Scalabrino, Gabriele Bavota, Rocco Oliveto
2023 J jnl
Automatically Generating Dockerfiles via Deep Learning: Challenges and Promises.
CoRR
Giovanni Rosa, Antonio Mastropaolo, Simone Scalabrino, Gabriele Bavota, Rocco Oliveto
2023 J jnl
Evaluating Code Summarization Techniques: A New Metric and an Empirical Characterization.
CoRR
Antonio Mastropaolo, Matteo Ciniselli, Massimiliano Di Penta, Gabriele Bavota
2023 J jnl
Log Statements Generation via Deep Learning: Widening the Support Provided to Developers.
CoRR
Antonio Mastropaolo, Valentina Ferrari, Luca Pascarella, Gabriele Bavota
2023 A* conf
On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot.
ICSE
Antonio Mastropaolo, Luca Pascarella, Emanuela Guglielmi, Matteo Ciniselli, Simone Scalabrino, Rocco Oliveto, Gabriele Bavota
2023 J jnl
On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot.
CoRR
Antonio Mastropaolo, Luca Pascarella, Emanuela Guglielmi, Matteo Ciniselli, Simone Scalabrino, Rocco Oliveto, Gabriele Bavota
2023 J jnl
Toward Automatically Completing GitHub Workflows.
CoRR
Antonio Mastropaolo, Fiorella Zampetti, Massimiliano Di Penta, Gabriele Bavota
2023 A* conf
Towards Automatically Addressing Self-Admitted Technical Debt: How Far Are We?
ASE
Antonio Mastropaolo, Massimiliano Di Penta, Gabriele Bavota
2023 J jnl
Towards Automatically Addressing Self-Admitted Technical Debt: How Far Are We?
CoRR
Antonio Mastropaolo, Massimiliano Di Penta, Gabriele Bavota
2023 J jnl
Using Transfer Learning for Code-Related Tasks.
IEEE Trans. Software Eng.
Antonio Mastropaolo, Nathan Cooper, David Nader-Palacio, Simone Scalabrino, Denys Poshyvanyk, Rocco Oliveto, Gabriele Bavota
2022 J jnl
An Empirical Study on the Usage of Transformer Models for Code Completion.
IEEE Trans. Software Eng.
Matteo Ciniselli, Nathan Cooper, Luca Pascarella, Antonio Mastropaolo, Emad Aghajani, Denys Poshyvanyk, Massimiliano Di Penta, Gabriele Bavota
2022 J jnl
Automated Variable Renaming: Are We There Yet?
CoRR
Antonio Mastropaolo, Emad Aghajani, Luca Pascarella, Gabriele Bavota
2022 A* conf
Using Deep Learning to Generate Complete Log Statements.
ICSE
Antonio Mastropaolo, Luca Pascarella, Gabriele Bavota
2022 J jnl
Using Deep Learning to Generate Complete Log Statements.
CoRR
Antonio Mastropaolo, Luca Pascarella, Gabriele Bavota
2022 A* conf
Using Pre-Trained Models to Boost Code Review Automation.
ICSE
Rosalia Tufano, Simone Masiero, Antonio Mastropaolo, Luca Pascarella, Denys Poshyvanyk, Gabriele Bavota
2022 J jnl
Using Pre-Trained Models to Boost Code Review Automation.
CoRR
Rosalia Tufano, Simone Masiero, Antonio Mastropaolo, Luca Pascarella, Denys Poshyvanyk, Gabriele Bavota
2022 J jnl
Using Transfer Learning for Code-Related Tasks.
CoRR
Antonio Mastropaolo, Nathan Cooper, David Nader-Palacio, Simone Scalabrino, Denys Poshyvanyk, Rocco Oliveto, Gabriele Bavota
2021 J jnl
An Adaptive Search Budget Allocation Approach for Search-Based Test Case Generation.
ACM Trans. Softw. Eng. Methodol.
Simone Scalabrino, Antonio Mastropaolo, Gabriele Bavota, Rocco Oliveto
2021 A conf
An Empirical Study on Code Comment Completion.
ICSME
Antonio Mastropaolo, Emad Aghajani, Luca Pascarella, Gabriele Bavota
2021 J jnl
An Empirical Study on Code Comment Completion.
CoRR
Antonio Mastropaolo, Emad Aghajani, Luca Pascarella, Gabriele Bavota
2021 J jnl
An Empirical Study on the Usage of Transformer Models for Code Completion.
CoRR
Matteo Ciniselli, Nathan Cooper, Luca Pascarella, Antonio Mastropaolo, Emad Aghajani, Denys Poshyvanyk, Massimiliano Di Penta, Gabriele Bavota
2021 A* conf
Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks.
ICSE
Antonio Mastropaolo, Simone Scalabrino, Nathan Cooper, David Nader-Palacio, Denys Poshyvanyk, Rocco Oliveto, Gabriele Bavota
2021 J jnl
Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks.
CoRR
Antonio Mastropaolo, Simone Scalabrino, Nathan Cooper, David Nader-Palacio, Denys Poshyvanyk, Rocco Oliveto, Gabriele Bavota
2013 C conf
Legal documents categorization by compression.
ICAIL
Antonio Mastropaolo, Francesco Pallante, Daniele Paolo Radicioni